Intelligent management methods, devices, equipment and media for the entire life cycle of precast components

By constructing a digital twin model and making intelligent decisions in the production of prefabricated components, the problem of data silos between subsystems was solved, multi-source data fusion and collaborative decision-making of the production line were realized, production efficiency and quality stability were improved, and a shift from passive response to proactive optimization was achieved.

CN123067355APending Publication Date: 2026-11-10CCCC FIRST HARBOR ENGINEERING CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610945286.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-06-29
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

In the production of precast components, the lack of data communication and collaboration between subsystems leads to production scheduling relying on manual experience, equipment status not being perceived in real time, process parameter adjustments being delayed, production cycle being difficult to optimize dynamically, equipment failures being mostly dealt with after the fact, quality consistency being difficult to guarantee, and overall production efficiency and intelligence level being limited.

Method used

By collecting multi-source production data and synchronizing it to a digital twin model, a high-fidelity dynamic image of the physical factory is constructed. The data is then processed in depth using an intelligent decision-making model to generate a composite instruction set covering cycle time, maintenance, and process. These instructions are then accurately fed back to the execution terminal, forming a closed-loop control.

Benefits of technology

It has enabled the fusion and collaborative decision-making of multi-source data, improved equipment utilization and order delivery efficiency, ensured quality stability and intelligent production level, and transformed into proactive optimization and closed-loop control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123067355A_ABST
    Figure CN123067355A_ABST
Patent Text Reader

Abstract

This invention discloses a method, device, equipment, and medium for intelligent management and control of the entire lifecycle of precast components. The method includes: collecting multi-source production data from multiple independent subsystems in a precast component production line; synchronizing the multi-source production data to a pre-constructed digital twin model to drive the digital twin model to update in real time; calling a preset intelligent decision-making model to process the multi-source production data gathered in the digital twin model to obtain a set of decision instructions for controlling the production line; and feeding back the set of decision instructions to the target control terminal and execution equipment corresponding to the production line to execute the control operations corresponding to the set of decision instructions. This invention achieves global collaborative optimization and closed-loop intelligent management and control based on digital twins and intelligent decision-making, effectively improving the intelligence level and efficiency of precast component production.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the fields of intelligent manufacturing and building industrialization, and in particular to a method, device, equipment and medium for intelligent management and control of the entire life cycle of prefabricated components. Background Technology

[0002] Currently, in the precast component manufacturing sector, production lines are typically equipped with automated subsystems such as warehouse control systems, manufacturing execution systems, and various IoT sensors to automate single-point operations. However, these subsystems often lack effective data communication and collaboration mechanisms, creating information silos. This leads to production scheduling relying on manual experience, inability to perceive equipment status in real time, and delayed adjustments to process parameters. This decentralized control model makes dynamic optimization of production cycle time difficult, equipment failures are mostly reactive, and the consistency of quality in key processes such as maintenance is hard to guarantee. Overall production efficiency and intelligence levels are limited. Therefore, there is an urgent need for an intelligent management and control method for the entire lifecycle of precast components that can achieve multi-source data fusion, global collaborative decision-making, and closed-loop intelligent control. Summary of the Invention

[0003] This invention provides a method, device, equipment, and medium for intelligent management and control of the entire life cycle of prefabricated components. Through the intelligent management and control method for the entire life cycle of prefabricated components, global collaborative optimization and closed-loop intelligent management and control based on digital twins and intelligent decision-making are achieved.

[0004] To achieve the above objectives, the technical solution created by this invention is implemented as follows: In a first aspect, the present invention provides a method for intelligent management and control of the entire life cycle of prefabricated components, the method comprising: Collect multi-source production data from multiple independent subsystems in the precast component production line; The multi-source production data is synchronized to the pre-built digital twin model to drive the digital twin model to be updated in real time. The preset intelligent decision-making model is invoked to process the multi-source production data gathered in the digital twin model to obtain a set of decision instructions for controlling the production line; The decision instruction set is fed back to the target control terminal and execution equipment corresponding to the production line to execute the control operation corresponding to the decision instruction set.

[0005] Furthermore, the collection of multi-source production data from multiple independent subsystems in the precast component production line includes: The first type of data is collected from the warehouse control system. This first type of data includes the identification and flow location status information of molds and components in the production line conveying equipment, elevators and three-dimensional maintenance warehouse. The second type of data is collected from the manufacturing execution system. This second type of data is data that is bound to the component production order, including component process drawing information and quality inspection information. A third type of data is collected from IoT sensors deployed at the production site, including operating parameter information of the production equipment and environmental status information of the curing kiln.

[0006] Furthermore, synchronizing the multi-source production data to the pre-built digital twin model to drive the digital twin model to perform real-time updates includes: Using Building Information Modeling (BIM) as the geometric and information foundation, a digital twin model is constructed, which includes a production line layout model, a production equipment model, and a component model. Establish a data mapping relationship between the virtual entities in the digital twin model and the physical entities in the production line; Based on the data mapping relationship, the first type of data, the second type of data, and the third type of data are injected into and the state attributes of the corresponding virtual entities in the digital twin model are updated respectively.

[0007] Furthermore, the step of invoking a preset intelligent decision-making model to process the multi-source production data aggregated in the digital twin model to obtain a set of decision instructions for controlling the production line includes: The preset intelligent decision-making model performs timestamp alignment and correlation fusion on the updated first type of data, second type of data and third type of data in the digital twin model to generate a full-process tracking data chain with a single component as the granularity. The preset intelligent decision-making model analyzes and calculates based on the full-process tracking data chain to generate a set of decision instructions that includes production cycle optimization instructions, equipment predictive maintenance instructions, and process parameter control instructions.

[0008] Furthermore, the generation of the decision instruction set, which includes production cycle optimization instructions, equipment predictive maintenance instructions, and process parameter control instructions, includes: The preset intelligent decision-making model extracts the current queue length and historical average operation time of each workstation based on the full-process tracking data chain, calculates the current bottleneck workstation of the production line through the preset blockage rate evaluation algorithm, and, in combination with the order delivery time window, reverse-derives and generates the production cycle optimization instruction with the minimum waiting time. The preset intelligent decision-making model is based on the full-process tracking data chain, extracts multi-dimensional operating parameters of the associated equipment to construct the equipment health baseline curve, and uses a sliding time window to monitor the real-time fluctuation trend of the parameters. When the degree of deviation of the parameters from the health baseline curve exceeds the preset dynamic threshold range, it is determined as a potential fault point and generates the equipment predictive maintenance instruction containing the urgency level and maintenance suggestions. The preset intelligent decision-making model is based on the full-process tracking data chain, analyzes the standard curing process curve corresponding to the current component type, and obtains the temperature and humidity distribution cloud map in the curing kiln in the digital twin model in real time. By comparing the deviation between the standard curve and the real-time distribution, it dynamically calculates the start and stop time and power ratio of the heating or humidifying equipment, and generates refined process parameter control instructions.

[0009] Furthermore, the step of feeding back the decision instruction set to the target control terminal and execution equipment corresponding to the production line includes: The production cycle optimization command is sent to the central scheduling controller of the production line to adjust the coordinated operation rhythm of each conveying device and robot on the production line. The predictive maintenance instructions for the equipment are pushed to the equipment management terminal interface and the mobile terminal of the maintenance personnel for visual alarms and maintenance prompts. The process parameter control commands are sent to the environmental control system of the curing kiln to perform precise temperature and humidity adjustments.

[0010] Furthermore, the method also includes: The system receives response data from the target control terminal and the execution device after performing the control operation, and inputs the response data as new multi-source production data into the digital twin model. Through the updating of the digital twin model and the processing of the preset intelligent decision model, a closed-loop intelligent control process for the production line is formed.

[0011] Secondly, the present invention provides an intelligent management and control device for the entire life cycle of prefabricated components, comprising: The data acquisition module is used to collect multi-source production data from multiple independent subsystems in the precast component production line; The synchronization module is used to synchronize the multi-source production data to the pre-built digital twin model to drive the digital twin model to be updated in real time. The processing module is used to call a preset intelligent decision-making model to process the multi-source production data gathered in the digital twin model to obtain a set of decision instructions for controlling the production line. The execution module is used to feed back the decision instruction set to the target control terminal and execution equipment corresponding to the production line, so as to execute the control operation corresponding to the decision instruction set.

[0012] Thirdly, the present invention provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; When the processor executes the computer execution instructions stored in the memory, it is used to implement the intelligent management and control method for the entire life cycle of prefabricated components as described in the first aspect of the invention.

[0013] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the intelligent management and control method for the entire life cycle of prefabricated components as described in the first aspect of the invention.

[0014] Through the aforementioned technical solution, this method constructs a high-fidelity dynamic mirror of the physical factory by collecting multi-source production data and synchronizing it to a digital twin model, thus solving the problem of lack of situational awareness caused by data silos in traditional systems. By deeply processing the fused data through an intelligent decision-making model, it generates a composite instruction set covering cycle time, maintenance, and processes, achieving a shift from passive response to proactive optimization. By accurately feeding these instructions back to the corresponding execution terminals and forming a closed loop, it ensures the effective implementation and continuous iteration of decisions. Overall, this method, with digital twins as the central hub, data chains as the link, and closed-loop feedback as the guarantee, systematically improves the level of intelligence in prefabricated component production, effectively increasing equipment utilization and order delivery efficiency while ensuring quality stability. Attached Figure Description

[0015] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart illustrating the intelligent management and control method for the entire lifecycle of prefabricated components provided in Embodiment 1 of the present invention. Figure 2 This is a schematic diagram of the intelligent management and control device for the entire life cycle of prefabricated components provided in Embodiment Six of the present invention; Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in Embodiment 7 of the present invention. Detailed Implementation

[0016] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0017] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, nor do they necessarily imply difference. It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner. In the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more.

[0018] It should be noted that the phrase "at...time" in the embodiments of this application can refer to the instant at which a certain situation occurs, or to a period of time after the occurrence of a certain situation; the embodiments of this application do not specifically limit this. Furthermore, the intelligent management and control method for the entire lifecycle of prefabricated components provided in the embodiments of this application is only an example, and the intelligent management and control method for the entire lifecycle of prefabricated components may also include more or less content.

[0019] To facilitate a clear description of the technical solutions in the embodiments of this application, some terms and technologies involved in the embodiments of this application will be briefly introduced below: Precast components: These are concrete structural parts, such as beams, slabs, columns, and walls, that are prefabricated in factories or prefabrication yards. After curing to their design strength, they are transported to the construction site for assembly and installation. Compared with traditional on-site casting methods, precast components have advantages such as high production efficiency, good quality control, and short construction cycles, and are widely used in engineering fields such as highway bridges, rail transit, and prefabricated buildings.

[0020] Warehouse Control System (WCS): This is a real-time control layer software system situated between the upper-level warehouse management system and the lower-level logistics execution equipment. In this application, the WCS is primarily responsible for managing the scheduling and status monitoring of logistics equipment such as mold trolleys, conveyor lines, elevators, and automated curing warehouses in the precast component production line, and for collecting and reporting in real-time the identification and location status information of molds and components at each node of the production line.

[0021] Manufacturing Execution System (MES) is an information management system for the shop floor production layer. It is responsible for breaking down enterprise-level production plans into executable work orders and for real-time tracking and recording of information such as materials, processes, and quality during the production process. In this application, the MES primarily carries data bound to component production orders, including component process drawing information (such as BIM model version number and concrete mix design parameters) and quality inspection information (such as quality inspection pass standards and planned completion times for each process).

[0022] The Internet of Things (IoT) refers to a network system that connects objects in the physical world to the internet through various sensors, RFID devices, GPS, and other information collection devices, according to agreed communication protocols, to achieve intelligent identification, positioning, tracking, monitoring, and management. In this application, an IoT sensor array is deployed at the production site to collect operating parameter information of production equipment (such as vibration, current, and rotational speed) and environmental status information of the curing kiln (such as temperature and humidity).

[0023] Building Information Modeling (BIM) is an engineering information integration and management technology based on three-dimensional digital models. It establishes virtual three-dimensional models of building projects and uses digital technology to endow the models with complete physical information, functional characteristics, and temporal data. In this application, BIM serves as the geometric and information foundation of the digital twin model, providing three-dimensional geometric representations and attribute data for production line layout models, production equipment models, and component models.

[0024] A digital twin is a virtual model that digitally maps a physical entity, process, or system with high fidelity and dynamic representation. A digital twin not only contains the static geometry and attribute information of the physical entity but also achieves synchronous updates with the physical entity through real-time data-driven processes, thus reflecting the current actual operating status of the physical entity. In this application, the digital twin model is built based on BIM and includes a production line layout model, a production equipment model, and component models. It achieves real-time updates of the virtual entity's state attributes by receiving multi-source production data.

[0025] Radio Frequency Identification (RFID) is a non-contact automatic identification technology that automatically identifies target objects and acquires relevant data through radio frequency signals. It requires no manual intervention and can operate in various harsh environments. In this application, RFID tags are attached to mold trolleys or components to obtain real-time identification and flow location information for each trolley and its supporting components in the automated warehouse, including precise warehouse location coordinates, entry and exit times, and movement speed on the conveyor line.

[0026] A Programmable Logic Controller (PLC) is a digital electronic system designed specifically for industrial environments. It uses programmable memory to store instructions for performing logical operations, sequential control, timing, counting, and arithmetic operations, and controls various mechanical equipment or production processes through digital or analog input / output interfaces. In this application, the PLC acts as the control terminal for the underlying execution equipment on the production line, receiving control commands such as speed change and pause commands from the intelligent management system and driving the corresponding equipment to execute them.

[0027] Automated Guided Vehicle (AGV): A transport vehicle equipped with electromagnetic or optical automatic guidance devices, capable of traveling along a prescribed path, and possessing safety protection and various transfer functions. In this application, the AGV is used for the automatic transfer of prefabricated components between different workstations, and its operating rhythm is controlled by production cycle optimization instructions.

[0028] Rail-guided vehicles (RGVs) are automated material handling equipment that run on fixed tracks. They achieve precise positioning through track guidance and are commonly used for storing, retrieving, and moving goods in automated warehouses. In this application, the RGV serves as a material handling device in an automated curing warehouse, responsible for delivering or retrieving trolleys carrying components into or from designated curing locations.

[0029] Network Time Protocol (NTP) is an Internet protocol used to synchronize the clocks of devices in a computer network. Through a layered time source structure, it enables devices in the network to synchronize their local clocks with a high-precision reference clock source, achieving millisecond-level or even higher time consistency. In this application, each subsystem, upon connecting to the intelligent management system, synchronizes its clock with the central clock server via NTP at the millisecond level to eliminate accumulated deviations in the local clocks of each subsystem, providing a unified time reference for subsequent timestamp alignment.

[0030] A message queue is an asynchronous communication mechanism. The sender stores a message in the queue and can continue performing other tasks, while the receiver retrieves the message from the queue for processing at an appropriate time. Message queues provide decoupling, peak shaving, and asynchronous processing. In this application, the message queue is used for data push in an event-driven mode. When a physical entity experiences a state change event, it is immediately pushed to the digital twin via the message queue, triggering a synchronous update of the corresponding virtual object's attributes.

[0031] End-to-end tracking data chain: This application defines a structured data organization form with a single component as the granularity. The data chain uses the component's unique identifier as the primary key and, through timestamp alignment and association fusion mechanisms, associates the flow location records from WCS, order and quality inspection records from MES, and equipment operation and environmental monitoring records from IoT sensors to the same component object, forming the complete life history data of the component from raw material entry to finished product exit.

[0032] Intelligent Decision Model: This is the standardized data processing and decision generation unit pre-defined in this application. The model takes the entire process tracking data chain as input and analyzes and calculates it through various built-in algorithm modules (including blockage rate assessment algorithm, equipment health baseline curve fitting, dynamic threshold determination, spatial deviation integral calculation, PID control algorithm, etc.), outputting a set of decision instructions that includes production cycle optimization instructions, equipment predictive maintenance instructions, and process parameter control instructions.

[0033] Production takt time refers to the time interval between two adjacent workstations on a production line completing one work cycle, and is a core indicator for measuring the rhythm of production line operation. Reasonable control of production takt time directly affects the production line's capacity utilization rate, work-in-process inventory level, and on-time order delivery rate. In this application, production takt time optimization instructions are dynamically generated through a congestion rate assessment and reverse derivation mechanism to achieve a production line operation rhythm with minimal waiting time.

[0034] Congestion rate: This is a quantitative indicator that measures the degree of material accumulation upstream due to insufficient downstream processing capacity at a certain workstation in a production line. In this application, the congestion rate is calculated using a comprehensive congestion rate evaluation algorithm. This algorithm considers two dimensions simultaneously: the ratio of the current queue length to the standard buffer capacity of the workstation, and the ratio of the current actual operation time to the historical average operation time. These dimensions are then weighted and fused using weighting coefficients.

[0035] Reverse scheduling is a scheduling method that starts from the end point. Unlike traditional forward scheduling, which calculates subsequent processes from the current state, reverse scheduling starts with the deadline of the order delivery window, deducts the standard operating time and process intervals of all necessary subsequent processes, and calculates the latest time that the current workstation must start work. This determines the maximum allowable waiting time and provides a time margin for cycle time adjustments.

[0036] Equipment health baseline curve: This is a dynamic baseline characterizing the "load-response" relationship of equipment in a healthy state. The curve uses equipment load rate as the independent variable and a weighted fusion value of multiple operating parameters (such as motor stator current, effective value of bearing vibration acceleration, and reducer housing temperature) as the dependent variable. It is obtained by regression analysis fitting of historical data collected under healthy operating conditions. Unlike traditional fixed standard values, this curve can dynamically adjust the health assessment benchmark according to changes in equipment load.

[0037] Sliding time window: This is a signal processing technique for smoothing time series data. The technique sets a fixed-length time window, which slides point-by-point along the time axis. The average of the data within the window is used as the smoothed output for the current point, thereby filtering out transient interference and random noise, and improving the signal-to-noise ratio. In this application, the length of the sliding time window is determined based on the mechanical response characteristics and fault evolution cycle of the target equipment.

[0038] Dynamic threshold range: This is a fault judgment threshold range that adaptively adjusts based on the real-time operating parameters of the equipment. Unlike traditional fixed threshold alarms, the upper and lower boundaries of the dynamic threshold range are adaptively scaled according to the current real-time load rate of the equipment, ambient temperature, and the cumulative running time of the equipment. This allows for a larger fluctuation range during high-load operation and automatically narrows the range under low-load or no-load conditions to improve detection sensitivity, thereby ensuring that the alarm logic always matches the current actual physical state of the equipment.

[0039] The standard curing process curve is a temperature-time variation specification that precast components should follow during the curing process. It typically includes three consecutive time periods: a heating stage, a constant temperature stage, and a cooling stage. The temperature change rate, target temperature, and duration of each stage are determined based on the concrete strength grade and mix proportion of the component. In this application, the standard curing process curve is digitally expressed as a multi-segment function model, serving as a calculable reference surface within the digital twin.

[0040] Temperature and humidity distribution cloud map: This is a visual representation formed by expanding the discrete point data of a limited number of physical sensors within the curing kiln into continuous three-dimensional spatial field data through spatial reconstruction technology. This cloud map reflects the real-time distribution of temperature and humidity at various spatial locations within the curing kiln, and can identify the specific location and volume of local cold or hot zones, providing a high-resolution spatial distribution data foundation for precise control. In this application, the temperature and humidity distribution cloud map is constructed using a Kriging interpolation algorithm or a radial basis function neural network.

[0041] Kriging interpolation is an optimal linear unbiased spatial interpolation method based on geostatistics. This algorithm not only considers the values ​​of known sampling points but also utilizes the spatial correlation between sampling points (i.e., the semi-variogram) to estimate values ​​at unknown locations, providing optimal interpolation results while minimizing the estimation variance. In this application, the Kriging interpolation algorithm is used to extend the temperature data from discrete sensor points within the curing kiln into continuous three-dimensional spatial field data.

[0042] Radial Basis Function Neural Network (RBFNN) is a feedforward neural network that uses radial basis functions as hidden layer activation functions. It boasts advantages such as simple structure, fast training speed, and strong nonlinear mapping capability, and is widely used in function approximation and spatial interpolation. In this application, RBFNN is used as an alternative to the Kriging interpolation algorithm to reconstruct discrete sensor data into a continuous three-dimensional temperature and humidity distribution field.

[0043] PID control algorithm: Short for Proportional-Integral-Derivative control algorithm, it is the most classic feedback control algorithm in industrial process control. This algorithm calculates the control output based on the deviation between the setpoint and the actual value using three components: a proportional term (proportional to the deviation), an integral term (time accumulation of the deviation), and a derivative term (rate of change of the deviation), to achieve precise adjustment of the controlled object. In this application, the PID control algorithm is used for fine-tuning the continuous opening of a heating steam valve or humidifying nozzle when the deviation is small.

[0044] Weighted moving average (WMA) is a statistical method for smoothing time series data. Unlike the simple moving average, which assigns equal weight to all data within a window, the WMA assigns different weight coefficients to data at different time points, typically with more recent data having a larger weight and more distant data having a smaller weight. This makes the smoothing result more reflective of the latest trends in the data. In this application, the WMA is used to calculate the historical average operation time for each workstation to eliminate the interference of a single abnormal operation on the overall cycle time assessment.

[0045] Least squares regression is a classic method for parameter estimation and curve fitting. Its core idea is to determine the model parameters by minimizing the sum of squared residuals between observed values ​​and model predictions, thereby obtaining the optimal fitted curve. In this application, least squares regression is used to fit historical data collected under the healthy operating conditions of equipment to obtain regression fitting functions of each monitoring parameter with respect to the load rate, and then construct the equipment health baseline curve.

[0046] Hydration reaction: This refers to the chemical reaction between cement and water to produce hydration products, and is the fundamental mechanism by which concrete acquires strength. The rate and extent of the hydration reaction are significantly affected by environmental factors such as temperature and humidity: excessively low temperatures can slow down or even stop the hydration reaction, resulting in slow strength development or frost damage to the concrete; excessively high temperatures may cause the hydration reaction to be too rapid, leading to micro-cracks inside the concrete. Therefore, precise control of temperature and humidity during curing is crucial to ensuring the final mechanical properties of precast components.

[0047] Model Predictive Control (MPC) is an advanced control strategy that uses an online rolling optimization method to solve for the optimal control sequence based on a mathematical model of the controlled object. In each control cycle, MPC predicts the system behavior over a finite time domain based on the current state and determines the optimal control action by solving a constrained optimization problem. It has a natural advantage in handling multivariable coupling and constraints. In this application, MPC is used as an alternative to the PID control algorithm, and can be used to output executable device action commands based on spatial deviation.

[0048] Example 1 Figure 1 This is a flowchart illustrating the intelligent management and control method for the entire lifecycle of prefabricated components provided in Embodiment 1 of the present invention, as shown below. Figure 1 As shown, the intelligent management and control method for the entire life cycle of precast components includes the following steps: S1. Collect multi-source production data from multiple independent subsystems of the precast component production line; In this embodiment, to break down information silos between automated subsystems in traditional precast component production and achieve global situational awareness, the collection of multi-source production data is further refined into three dimensions. Specifically, the first type of data is collected from the warehouse control system. This data includes the identification and location status information of molds and components in the production line conveying equipment, elevators, and automated curing warehouse. For example, by reading RFID tags or QR codes, the precise warehouse location coordinates, entry and exit times, and movement speed on the conveyor line of each trolley and its carried component are obtained in real time. This type of data constitutes the spatiotemporal trajectory basis of material flow. Simultaneously, the second type of data is collected from the manufacturing execution system. This data is bound to the component production order and includes component process drawings and quality inspection information. Specifically, when a component enters the production stage, the system automatically associates it with its corresponding BIM model version number, concrete mix parameters, quality inspection standards, and the planned completion time of the current process, ensuring a one-to-one correspondence between physical production and digital orders. Furthermore, the third type of data is collected from IoT sensors deployed on the production site. This data includes the operating parameters of the production equipment and the environmental status information of the curing kiln. For example, vibration sensors and current transformers can be used to collect real-time load and rotation speed data of the material placing machine and vibrating table, while temperature and humidity sensor arrays can be used to collect microenvironmental parameters of different areas within the curing kiln. It should be understood that although WCS, MES, and IoT are listed as three typical data sources above, in other implementations, energy consumption data from an energy management system (EMS) or image data from a video surveillance system (VMS) can also be accessed, as long as this data can reflect the operating status of the production line and support subsequent digital mapping.

[0049] S2. Synchronize the multi-source production data to the pre-built digital twin model to drive the digital twin model to be updated in real time; The core of this step lies in establishing a high-fidelity dynamic mapping between the physical world and the digital space, rather than a simple static 3D display. Specifically, using Building Information Modeling (BIM) as the geometric and information foundation, a digital twin model is constructed, including a production line layout model, a production equipment model, and component models. Based on this, a data mapping relationship is established between virtual entities in the digital twin model and physical entities in the production line. For example, a shuttle vehicle numbered "RGV-03" in the physical world is bound to its corresponding virtual RGV object in the digital space using a unique identifier. Specifically, this data mapping relationship is implemented through a pre-defined mapping configuration table. Each record in the mapping configuration table contains at least the physical entity's unique identifier, the virtual object's reference path, the data source type, the update trigger method, and the communication protocol fields. When the system starts, it automatically loads this mapping configuration table and completes the registration and binding of all virtual and physical entities. Then, based on the data mapping relationship, the first type of data, the second type of data, and the third type of data are injected into and the state attributes of the corresponding virtual entities in the digital twin model are updated. Regarding the update mechanism of state attributes, this embodiment adopts a hybrid triggering strategy combining event-driven and timed polling: for discrete state data such as location changes and equipment alarms, an event-driven mode is used, meaning that when a physical entity generates a state change event, it is immediately pushed to the digital twin via a message queue, triggering the synchronous update of the corresponding virtual object attributes; for continuous sensing data such as temperature and vibration, a timed polling mode is used, fetching the latest data in batches and refreshing the virtual object attributes at a preset sampling period (e.g., 200 milliseconds to 2 seconds, configured according to the parameter change rate). This hybrid triggering strategy effectively reduces the system's communication overhead and computational load while ensuring data real-time performance. It is particularly important to emphasize the "state attribute injection" mechanism, where the collected real-time data is not only used to display values ​​on the interface but is directly written as variables into the internal attribute fields of the virtual object, thereby changing the virtual object's behavior and appearance. For example, when an IoT sensor reports an overload of current in a vibrating table, the corresponding virtual vibrating table in the digital twin not only turns red as a warning but also its internal "health" attribute value decreases synchronously, triggering subsequent simulation or decision calculations. This mechanism ensures that the digital twin is a "living mirror image" of the physical factory, accurately reflecting the dynamic operating mechanism of the production line and providing a reliable virtual verification environment for intelligent decision-making.

[0050] S3. Call the preset intelligent decision-making model to process the multi-source production data gathered in the digital twin model to obtain a set of decision instructions for controlling the production line; Because the original multi-source data often differs in time scale and spatial granularity, directly using it for decision-making can lead to misjudgments. Therefore, this embodiment introduces a data governance step before decision-making. Specifically, the preset intelligent decision-making model performs timestamp alignment and correlation fusion on the updated first, second, and third types of data in the digital twin model to generate a full-process tracking data chain with a single component as the granularity. Specifically, timestamp alignment is divided into two levels: the first level is clock synchronization, where each subsystem synchronizes its clock with the central clock server of the intelligent control system at the millisecond level via Network Time Protocol (NTP) upon access, eliminating the cumulative deviation of the local clocks of each subsystem; the second level is sampling frequency alignment. Because there are differences in the event recording frequency of WCS (usually at the second level), the work order update frequency of MES (usually at the minute level), and the sampling frequency of IoT sensors (usually at the millisecond to hundred millisecond level), the system uses a linear interpolation method for time granularity alignment of low-frequency data sources. The interpolation formula is: Formula Description: Linear Interpolation Alignment Formula in The target moment to be aligned. This is the interpolated estimate for the target time. and These represent two actual sampling times adjacent to the target time in the low-frequency data source. and This corresponds to the actual sampled value. In the association and fusion phase, the system uses the component's unique identifier (component ID) as the primary key and, through multi-table join queries, associates the flow location records from WCS, order and quality inspection records from MES, and equipment operation and environmental monitoring records from IoT sensors under the same component object, forming a structured end-to-end tracking data chain. The data structure of this data chain can be represented as follows: Formula description: End-to-end tracking data chain structure in A unique identifier for a component. For components The entire process tracking data chain, This is a set of data on the component's location and status within the warehouse control system. This is the set of order and quality inspection data for this component in the manufacturing execution system. This refers to the set of IoT sensor data associated with the component. For example, the component's warehousing time recorded by WCS, the pouring completion time recorded by MES, and the curing temperature curve recorded by IoT are uniformly calibrated onto a millisecond-level system timeline and concatenated using the component ID as the primary key to form the complete lifecycle data of the component from raw material entry to finished product exit. Based on this high-quality end-to-end tracking data chain, a pre-set intelligent decision-making model performs analysis and calculations to generate a set of decision instructions, including production cycle optimization instructions, equipment predictive maintenance instructions, and process parameter control instructions. In this embodiment, the intelligent decision-making model is regarded as a standardized processing unit. Its input end receives the structured end-to-end tracking data chain, and its output end produces an executable set of instructions. The specific algorithm logic (such as blockage rate assessment, health baseline curve fitting, etc.) will be detailed in subsequent embodiments. Here, only its data interface and functional boundaries are defined. By constructing an end-to-end tracking data chain, this embodiment solves the problem of multi-source data discretization and fragmentation, enabling the decision-making model to make comprehensive judgments based on complete contextual information, significantly improving the accuracy and robustness of decision-making.

[0051] S4. Feed back the decision instruction set to the target control terminal and execution equipment corresponding to the production line to execute the control operation corresponding to the decision instruction set.

[0052] To ensure the accurate implementation of decision-making results, this embodiment designs a hierarchical and categorized instruction routing mechanism. Specifically, production cycle optimization instructions are sent to the central scheduling controller of the production line to adjust the coordinated operation rhythm of various conveying equipment and robots on the production line. For example, when the decision model determines that the next process is about to become congested, it directly sends speed change or pause instructions to the PLC or WCS main controller to achieve adaptive adjustment of the production line cycle. Predictive maintenance instructions are pushed to the equipment management terminal interface and the mobile terminals of maintenance personnel for visual alarms and maintenance prompts. This allows maintenance personnel to receive work orders containing information on the fault location, possible causes, and suggested spare parts before a fault occurs, transforming passive repair into proactive prevention. Process parameter control instructions are sent to the environmental control system of the curing kiln to perform precise temperature and humidity adjustments. For example, the opening percentage of steam valves or the frequency of the blower are calculated based on real-time deviations and directly written into the setpoint register of the environmental control system. It should be understood that the above instruction distribution path is only a preferred example. In actual deployment, some instructions can also be merged and distributed or forwarded through edge computing gateways, depending on the on-site network architecture or management permission configuration, as long as the instructions can accurately reach the corresponding execution entity. This refined feedback mechanism breaks down the final barrier from the "digital brain" to the "physical hands and feet," ensuring the effective closure of the intelligent control loop.

[0053] S5. Receive the response data fed back by the target control terminal and the execution device after performing the control operation, and input the response data as new multi-source production data into the digital twin model. Through the updating of the digital twin model and the processing of the preset intelligent decision model, a closed-loop intelligent control process for the production line is formed.

[0054] This step is crucial for enabling the system's self-evolution and continuous optimization. Specifically, after the executing equipment receives and acts on a command, the system collects its actual response status in real time. For example, after issuing a command to adjust the steam valve opening, the system not only records the command value but also monitors the actual temperature change curve inside the kiln through a temperature sensor, and re-injects this "execution effect" data as a new third type of data into the digital twin. If the actual heating rate is lower than expected, the environmental model parameters in the digital twin will be automatically corrected, and the intelligent decision-making model will output compensation commands based on the corrected model in the next round of calculation. This dynamic iterative process of "perception-decision-execution-feedback-re-perception" enables the system to adapt to uncertainties such as equipment aging and environmental drift, ensuring long-term operational stability and control accuracy.

[0055] Through the steps S1 to S5 described above, this embodiment constructs a complete backbone process for the intelligent management and control method of the entire life cycle of prefabricated components. This process starts with multi-source data acquisition, uses digital twins as carriers, a full-process tracking data chain as a link, hierarchical instruction feedback as a means, and closed-loop response iteration as a guarantee, thus establishing a unified data context and execution environment upon which each subsequent specific algorithm branch depends.

[0056] Example 2 In this second embodiment, to address the issue of wasted production capacity due to poor process coordination during prefabricated component production, the generation logic of production cycle optimization instructions is further refined. Specifically, the preset intelligent decision-making model extracts the current queue length and historical average operation time of each workstation based on the full-process tracking data chain. It calculates the current bottleneck workstation of the production line through a preset congestion rate evaluation algorithm and, combined with the order delivery time window, reverse-engineers and generates production cycle optimization instructions with minimum waiting time.

[0057] This generation logic is not a simple linear calculation, but a bidirectional coupled solution process based on real-time state and future constraints. First, regarding data feature extraction, the system does not merely read the current instantaneous queue values, but rather parses the work completion records of each workstation within a preset time period (e.g., the last 4 hours) from the end-to-end tracking data chain. The historical average work time is then calculated using a weighted moving average method, with the following formula: ,in For workstation number, For workstation The historical average operation time, The number of job records to be traced. For the job record number ( ), For workstation No. The actual time spent on this task. The corresponding weight coefficients and satisfying The weights are progressively reduced from nearest to furthest in time (e.g., using an exponential decay method) to eliminate the interference of a single abnormal operation on the overall cycle time assessment. Simultaneously, the current queue length includes not only the number of components physically waiting in the buffer zone but also virtual queue members predicted to arrive in the next cycle time based on the upstream conveyor line speed, thus enabling prediction of congestion trends.

[0058] Secondly, in the bottleneck identification stage, this embodiment employs a dynamic congestion rate assessment algorithm, rather than relying on a fixed capacity design value. Specifically, the congestion rate is calculated using the following formula: ;in, For the first Overall congestion rate of each workstation This is the current queue length for this workstation (including the physical queue and the predicted virtual queue). This is the standard buffer capacity for this workstation. This represents the actual working time currently consumed at this workstation. This represents the historical average operation time for this workstation. and The weighting coefficients are and satisfy the following conditions: When a certain workstation When a workstation exceeds a preset dynamic threshold range, it is identified as the current bottleneck on the production line. It should be understood that this dynamic threshold range is not static but adaptively adjusted based on the current shift's production load rate. For example, during peak production periods, the system can appropriately raise the threshold for triggering bottleneck warnings to avoid fluctuations caused by frequent speed adjustments; while during low-load periods, the threshold is lowered to improve response sensitivity. This mechanism ensures that bottleneck identification possesses both statistical stability and agility in responding to unexpected situations.

[0059] Furthermore, after identifying the bottleneck workstation, this embodiment introduces a reverse derivation mechanism to generate the final cycle time instruction. Unlike the traditional method of forward scheduling based solely on the current queue state, the mathematical model for reverse derivation is as follows: starting from the order delivery time window's deadline, deducting the standard operation time of all subsequent necessary processes and necessary process intervals, the latest possible start time for the current bottleneck workstation is calculated. The calculation formula is as follows: ;in, Bottleneck workstation The latest time when the work must begin. This is the deadline for order delivery. From workstation The total number of processes between the final outbound workstation and the final delivery station. This is an index for traversing processes from the first process downstream of the bottleneck station to the final outbound station. For downstream Standard operating time for each process For the first The necessary process interval after each operation is completed. Based on this, the system calculates the allowable waiting time between the current moment and the critical moment: ;in, For workstation Maximum allowed waiting time The bottleneck station calculated by formula (4) The latest time when the work must begin. This is the current system time. If... This indicates that the current time is earlier than the limit time. Based on this, the system issues deceleration or pause commands to upstream equipment to smoothly reduce the speed of the upstream cycle. This indicates that the current moment is approaching or has exceeded the limit, and the system immediately triggers acceleration or priority passage commands. Through this end-to-end calculation method, the system unifies the originally discrete workstation control under the global delivery goal, ensuring that every cycle adjustment action serves the achievement of the final delivery node.

[0060] To more intuitively demonstrate the technical advantages of this embodiment, it is compared with the traditional fixed-cycle mode and the simple forward scheduling mode. Assume that in a T-beam precast production line, the processing capacity of the curing kiln inlet station decreases by 30% due to a temporary equipment speed reduction. If the traditional fixed-cycle mode is used, the upstream pouring station continues production at the original rate, inevitably leading to a large accumulation of wet billets in front of the kiln. This not only occupies valuable buffer resources but may also affect the initial setting quality of the concrete due to excessive waiting time. If forward scheduling based solely on the current queue is used, although it can trigger upstream deceleration after accumulation occurs, it often has a lag and cannot determine whether the deceleration will affect the timely delivery of subsequent orders. However, using the reverse deduction mechanism of this embodiment, the system immediately performs a reverse calculation based on the delivery deadline of subsequent components upon detecting an increase in the curing kiln inlet operation time. If calculations determine that even with a temporary slowdown in upstream processes, subsequent components still have sufficient time to complete curing, the system will precisely issue a cycle time command matching the current post-slowdown processing capacity. This allows the upstream pouring rhythm to smoothly transition to a new equilibrium point, avoiding ineffective accumulation of wet blanks and ensuring that subsequent orders are not affected. Actual verification shows that, compared to traditional methods, this embodiment can reduce the average ineffective waiting time between processes by more than 40% when facing sudden order insertions or equipment speed reductions, significantly improving the production line's flexibility and overall operational efficiency.

[0061] Example 3 In this third embodiment, to address the frequent unplanned downtime of key equipment in the precast component production line, the generation logic of predictive maintenance instructions is further refined. Specifically, the preset intelligent decision-making model, based on the full-process tracking data chain, extracts multi-dimensional operating parameters of related equipment to construct an equipment health baseline curve. A sliding time window is used to monitor the real-time fluctuation trend of these parameters. When the deviation of parameters from the health baseline curve exceeds a preset dynamic threshold range, it is identified as a potential fault point, and a predictive maintenance instruction containing the urgency level and repair suggestions is generated.

[0062] The core of this generation logic lies in establishing a deep binding relationship between the physical state of the equipment and the digital model, rather than simply triggering alarms for numerical over-limits. Firstly, regarding the construction of the equipment health baseline curve, the system does not use a single-dimensional fixed standard value, but rather extracts multi-dimensional operating parameters of the equipment under different working conditions from the entire process tracking data chain for joint modeling. Specifically, the multi-dimensional operating parameters include at least the motor stator current, the effective value of bearing vibration acceleration, and the gearbox housing temperature. When constructing the equipment health baseline curve, the intelligent decision-making model uses the equipment load rate as the independent variable and the weighted fusion value of the above multi-dimensional parameters as the dependent variable. Through regression analysis of historical normal production data, it fits a dynamic baseline characterizing the "load-response" relationship of the equipment in a healthy state. The mathematical expression of this health baseline curve is as follows: ;in, For the equipment at the load rate The comprehensive health benchmark value is as follows. The current load rate of the device (value range: 0 to 100%). To monitor the number of parameter dimensions (in this embodiment) These correspond to the motor stator current, the effective value of bearing vibration acceleration, and the reducer housing temperature, respectively. Dimension index for monitoring parameters ( ), For the first Normalized weight coefficients of each parameter and satisfying , For the first The model employs a regression function with respect to load rate, obtained through least-squares regression of historical data collected during the equipment's healthy operating conditions. For example, the health baseline curve for a concrete placing boom's vibrating motor is a vibration-current coupling curve that rises gradually with increasing load, rather than a horizontal straight line. This benchmark construction method based on operating condition correlation ensures that the model can accurately distinguish between "normal high-load operation" and "abnormal low-load failure," laying a physical foundation for subsequent accurate diagnosis.

[0063] Secondly, to eliminate transient interference and random noise in the sensor-acquired data, this embodiment introduces a sliding time window mechanism to smooth the real-time data. The length of the sliding time window is not arbitrarily set, but determined based on the mechanical response characteristics and fault evolution cycle of the target device. Specifically, for high-frequency vibration signals, the window length is usually set to an integer multiple of the device's rotation cycle (e.g., 10 to 20 rotation cycles) to retain periodic characteristics and filter out asynchronous noise; for parameters with high thermal inertia, such as temperature, the window length is set on the order of minutes to reflect the true heat accumulation trend. It should be understood that although the above describes a window setting method based on physical characteristics, in other embodiments, an adaptive window algorithm can also be used to automatically adjust the window size according to the real-time changes in data variance, as long as a balance between noise suppression and fault response speed can be achieved. The formula for smoothing the original sampled data using the sliding time window is as follows: ;in, For the first The output value after smoothing of each sampling point The length of the sliding time window (in terms of the number of sampling points). For the first The original collected values ​​of each sampling point For the backtracking index within the window ( For high-frequency vibration signals, Take the number of sampling points corresponding to an integer multiple of the equipment's rotation cycle (e.g., 10 to 20 rotation cycles); for thermal inertial parameters such as temperature, The number of sampling points corresponding to a minute-level time span is selected; the sliding step size is 1 sampling point by default, i.e., sliding point by point. Through the filtering process of the sliding time window, the data sequence entering the threshold determination stage has a higher signal-to-noise ratio, effectively avoiding false alarms caused by instantaneous spike pulses.

[0064] Furthermore, this embodiment employs a dynamic threshold range as the core criterion for fault determination, which is the key difference from traditional static threshold alarms. The upper and lower boundaries of the dynamic threshold range are not fixed but adaptively scaled based on the device's current real-time load rate, ambient temperature, and cumulative device runtime. The calculation formula is as follows: ; ;in, and Current load rate The upper and lower limits of the dynamic threshold range. The health baseline value is calculated using formula (6). The basic deviation tolerance (determined by the equipment's factory calibration data). This is the load sensitivity coefficient (reflecting the degree to which the allowable fluctuation range is widened under high load). The environmental temperature sensitivity coefficient, The current ambient temperature. This is the aging compensation coefficient. This represents the cumulative runtime of the device.

[0065] Specifically, when the equipment is under high load, the allowable vibration and temperature fluctuation range will be widened accordingly due to increased mechanical stress, and the width of the dynamic threshold range will expand proportionally. Conversely, under low load or no-load conditions, the threshold range will automatically narrow to improve detection sensitivity. Furthermore, as the equipment's service life increases, the health baseline curve itself will slowly drift, and the dynamic threshold range will also introduce an aging compensation factor related to the equipment's cumulative operating time, allowing the judgment criteria to be gradually adjusted to follow the equipment's natural degradation process. For example, during the operation of a gantry crane, when the hoisting motor load rate reaches 85% and the ambient temperature is 35℃, the system will dynamically adjust the vibration alarm upper limit from the default 4.5mm / s to 6.2mm / s; while when the motor is in standby mode, the alarm upper limit will automatically drop back to 2.0mm / s. This mechanism ensures that the alarm logic always matches the current actual physical state of the equipment. Based on this, this embodiment defines the following potential fault point judgment rules: Rule 1 is continuous limit exceedance judgment, when the parameter value after sliding window smoothing... continuous sampling points ( The preset number of confirmation points (e.g., 5 to 10 consecutive sampling points) exceeds the dynamic threshold range. When the parameter value is continuously..., it is identified as a potential fault point; Rule 2 is the trend slope determination, when the parameter value is continuously... linear regression slope within each sampling point The absolute value exceeds the preset rate of change threshold. Even if the parameter value has not yet exceeded the limit, it is still identified as a potential fault point to capture gradual faults in their nascent stage. When any of the above rules is triggered, the system generates predictive maintenance instructions for the equipment, which include an urgency rating (based on a comprehensive assessment of the extent and duration of the exceedance) and maintenance suggestions (based on matching the deviation parameter type to a preset fault knowledge base).

[0066] In traditional models, alarm thresholds are typically set once and remain unchanged during equipment installation and commissioning. However, precast component production equipment operates in harsh environments characterized by heavy loads, dust, and drastic temperature and humidity fluctuations. As components wear and age, the equipment's normal operating parameters gradually deviate from the initial settings. Continuing to use the factory-set fixed thresholds can easily lead to two serious defects: first, false alarms, where equipment, though aged, remains within safe operating limits but triggers frequent false alarms due to parameters slightly exceeding the fixed thresholds, causing maintenance personnel to overlook genuine potential problems; second, missed alarms, where under light loads or low temperatures, certain early fault characteristics are masked by the broad fixed thresholds, failing to provide timely warnings until catastrophic shutdowns occur. In contrast, this embodiment employs a combined strategy of "health baseline curve + sliding window + dynamic threshold," achieving dynamic adaptation of alarm standards by real-time sensing of changes in operating conditions and equipment status evolution. Verified on actual production lines, this embodiment can reduce the false alarm rate of equipment fault warning by more than 60% compared with the fixed threshold mode, while extending the detection lead time of early faults by an average of 48 hours, significantly improving the accuracy and practicality of predictive maintenance and providing a reliable guarantee for the continuous and stable operation of the production line.

[0067] Example 4 In this fourth embodiment, to address the quality fluctuations caused by lax environmental control during the curing of precast components, the generation logic of process parameter control instructions is further refined. Specifically, the preset intelligent decision-making model, based on a full-process tracking data chain, analyzes the standard curing process curve corresponding to the current component type and acquires the temperature and humidity distribution cloud map inside the curing kiln in the digital twin model in real time. By comparing the deviation between the standard curve and the real-time distribution, the start-up and shutdown times and power ratios of the heating or humidifying equipment are dynamically calculated, generating refined process parameter control instructions.

[0068] The core of this generation logic lies in elevating environmental control from the traditional "single-point threshold feedback" to a "spatial distribution feedback" dimension, to adapt to the complex conditions of large-volume, multi-batch collaborative curing of precast components. Firstly, regarding the digital representation of the standard curing process curve, the system does not merely store static temperature-time tables, but constructs them as a multi-segment function model incorporating heating rate, constant temperature accuracy, cooling gradient, and humidity coupling constraints. The piecewise function expression of the standard curing process curve is as follows: ; in, The maintenance process time (starting from the start of maintenance). For a moment Standard maintenance temperature value, To maintain the initial curing temperature, The heating rate is expressed in °C / h. This marks the end of the warming phase. The target temperature for the isothermal stage (the accuracy is usually controlled within ±2℃). This marks the end of the constant temperature phase. The cooling gradient rate is expressed in °C / h. This marks the end of the entire curing cycle. The duration and temperature parameters for each stage are automatically matched and loaded from a pre-set process parameter library based on the concrete strength grade and mix proportion of the component. Specifically, for concrete components with different strength grades and mix proportions, the intelligent decision-making model reads its process formula ID from the end-to-end tracking data chain, automatically loads the corresponding standardized curing regime, and transforms it into a calculable reference surface within the digital twin. It should be understood that although this embodiment uses a standard curing regime as an example, in other embodiments, this reference can also be an optimization curve generated by self-learning based on historical high-quality production data, as long as it can characterize the environmental evolution path required for the component to achieve the target performance.

[0069] Secondly, to obtain a temperature and humidity distribution cloud map reflecting the actual environment inside the kiln, this embodiment employs a spatial reconstruction technology based on multi-source data fusion. Specifically, the system first collects real-time readings from a limited number of physical sensors located at different positions within the curing kiln. Then, combining this with a pre-calibrated kiln thermal characteristics and flow field simulation model in a digital twin, the discrete point data is expanded into continuous three-dimensional spatial field data using Kriging interpolation or a radial basis function neural network. For example, when a sensor in the middle of the kiln shows a normal temperature, but the corner sensor reading is low, the system does not simply take the average value, but instead identifies the specific location and volume of the local cold zone through cloud map reconstruction. Furthermore, in the deviation calculation stage, this embodiment introduces an evaluation mechanism combining spatial integration and key point weighting. The intelligent decision-making model does not compare a single value, but rather performs a voxel-by-voxel comparison between the real-time temperature and humidity distribution cloud map and the desired field defined by the standard process curve. Specifically, a higher weight coefficient is assigned to the core area where components are densely placed; for the edge areas near the kiln wall or air duct, a corresponding tolerance threshold is set based on the actual impact on component quality. The formula for calculating the deviation can be expressed as follows: ;in, This represents the effective temperature deviation experienced by the internal components of the curing kiln at the current control moment. To maintain the effective curing space volume of the kiln, The three-dimensional spatial coordinates inside the kiln coordinates Spatial weight function at the location, Coordinates inside the kiln The real-time temperature value at the location, This is the current maintenance progress time. For a moment The corresponding standard curing temperature value (determined by formula (10)). The system uses a volumetric infinitesimal element. Through this weighted integral calculation, the system can quantify the "effective deviation" that truly affects the hydration reaction process of the component, avoiding unnecessary equipment actions triggered by instantaneous fluctuations in non-critical areas and improving the robustness of the control strategy.

[0070] Based on this, the system maps the calculated effective deviation to specific equipment control parameters. Specifically, the intelligent decision model incorporates a hybrid solver combining an improved PID control algorithm and a fuzzy lookup table method. When the deviation is small, the PID algorithm is used for fine-tuning, and its discretized control output formula is as follows: ;in, This is the sequence number of the current control cycle (incrementing sequentially since the start of control). For the first The equipment control output (i.e., the opening percentage of the heating steam valve or humidifying nozzle) for each control cycle. This is the proportional gain coefficient. This is the integral gain coefficient. The differential gain coefficient, For the first Deviation per control cycle , For the first Deviation per control cycle To control the sampling period, Index for cumulative integration ( ), For the first The deviation amount per control cycle. System output. The system continuously adjusts the opening percentage to ensure a smooth environmental transition. When the deviation is large or shows a rapid changing trend, it switches to a fuzzy lookup table mode to directly match a preset combination of strong intervention strategies, such as simultaneously starting the high-speed mode of the circulating fan and the auxiliary heater, and providing a clear start-stop sequence. It should be understood that the above solution method is only a preferred example. In practical applications, model predictive control (MPC) or reinforcement learning algorithms can also be used, as long as they can output executable equipment action commands based on the spatial deviation. Through this hierarchical response mechanism, the system ensures both steady-state control accuracy and rapid adjustment capability to cope with sudden disturbances.

[0071] To more intuitively demonstrate the technical advantages of this embodiment, a comparison with the traditional single-point temperature control mode is provided below. In the traditional mode, the curing kiln typically relies on a single temperature sensor at its center for feedback control. However, due to the large size and tight stacking of prefabricated components, dead air zones and thermal hysteresis effects inevitably exist within the kiln. When the temperature at the center point reaches the target, the edge areas may still be at low temperatures, leading to slow strength development or even freezing of components in those areas; conversely, if the overall set temperature is increased to accommodate the edges, the components in the center area may develop micro-cracks due to overheating. This "one-sided" control dilemma stems from a lack of perception and control over the spatial distribution of the environment. In contrast, this embodiment achieves "on-demand heating and precise humidification" by constructing a temperature and humidity distribution cloud map and implementing spatial weighted deviation calculation. Verified on actual production lines, compared to traditional single-point temperature control, the method in this embodiment reduces the maximum temperature difference in the curing kiln from ±5℃ to within ±1.5℃, and the standard deviation of the 28-day compressive strength of components in the same batch is reduced by more than 40%, significantly improving the consistency and pass rate of product quality, and fundamentally solving the problem of component performance dispersion caused by uneven environment.

[0072] Example 5 In this fifth embodiment, the system integration application and comprehensive technical effects of the intelligent management and control method for the entire life cycle of precast components described in the preceding embodiments will be further illustrated by combining the actual production scenario of the precast beam yard in a highway reconstruction and expansion project. It should be understood that this embodiment aims to verify the practicality and synergistic efficiency of the technical solution of the present invention through specific application scenarios, rather than to redefine or reduce the aforementioned technical features.

[0073] Specifically, an intelligent control system based on the method of this invention was deployed in the T-beam prefabrication plant of a highway reconstruction and expansion project. The beam yard is equipped with an automated rebar processing line, a concrete pouring line, a three-dimensional curing kiln, and an AGV transfer system. At the data perception level, the warehouse control system collects real-time RFID identification and location status of each mold trolley at the pouring station, curing kiln, and beam storage area; the manufacturing execution system simultaneously issues order information, BIM model parameters, and quality inspection standards for each T-beam; and IoT sensor arrays deployed at the mixing plant, concrete placing boom, curing kiln, and boiler room continuously transmit equipment operating parameters and environmental status data. These data, through the timestamp alignment and correlation fusion mechanism described in Example 1, construct a full-process tracking data chain at the granularity of a single T-beam in the digital twin model, providing a unified and high-fidelity data context for subsequent intelligent decision-making.

[0074] To more intuitively demonstrate the mechanism of multi-module collaborative operation, a typical abnormal operating condition handling process is used as an example below. When the digital twin model detects that the temperature distribution cloud map of zone 3 of the curing kiln deviates from the standard curing curve, the system does not handle the environmental problem in isolation, but triggers a cross-dimensional linkage response. First, based on the process parameter control logic described in Example 4, the intelligent decision model calculates the target opening degree of the steam valve and the frequency conversion frequency of the circulating fan by comparing the spatial deviation between the real-time temperature and humidity distribution cloud map and the standard curve, and directly sends the refined process parameter control instructions to the curing kiln environmental control system to achieve rapid and accurate compensation for the microenvironment of zone 3. At the same time, based on the equipment predictive maintenance logic described in Example 3, the system finds, when analyzing the full-process tracking data chain, that the effective value of the vibration acceleration of the boiler induced draft fan supplying heat to zone 3 shows an upward trend within the sliding time window, and the degree of deviation from the healthy baseline curve has exceeded the dynamic threshold range corresponding to the current load rate. Based on this, the system determines that the wind turbine has a potential failure risk of bearing wear, and immediately generates a predictive maintenance instruction for the equipment, which includes an urgency rating and maintenance recommendations. This instruction is then pushed to the equipment management terminal and the mobile terminal of the maintenance personnel, prompting them to arrange preventive replacement after the current maintenance cycle ends.

[0075] More importantly, the abnormal signals from the two independent dimensions mentioned above were correlated and analyzed at the global level by the intelligent decision-making model. Considering that Zone 3 is undergoing temperature control compensation and the boiler fan is about to enter the maintenance window, the actual effective curing capacity of this area is temporarily reduced. At this time, according to the production cycle optimization logic described in Example 2, the system automatically triggers the reverse derivation mechanism: using the delivery time window of the affected batch of T-beams as a constraint, combined with the current efficiency reduction state of Zone 3 and the queuing length of subsequent processes, the maximum allowable production rhythm of the upstream pouring station is recalculated. Subsequently, the system sends the production cycle optimization instruction containing deceleration or pause instructions to the central scheduling controller, so that the upstream pouring line and AGV transfer rhythm can smoothly adapt to the temporary capacity bottleneck of the curing kiln. This linkage mechanism avoids the ineffective accumulation of wet billets in front of the kiln due to blind production, and also prevents the risk of concrete initial setting quality caused by excessive waiting time, truly realizing global collaborative optimization from environmental control, equipment operation and maintenance to production scheduling.

[0076] Through six months of continuous operation verification at the T-beam prefabrication plant, the method of this invention demonstrated significant technical effects. Compared to the traditional model relying on manual experience and decentralized subsystem control, the unplanned downtime at the beam yard was reduced by more than 30% after adopting this invention. This is mainly due to the fact that predictive maintenance instructions move the fault handling point forward, avoiding the impact of sudden disaster-induced shutdowns on production continuity. Simultaneously, the T-beam finished product curing qualification rate increased to 99.5%, and the standard deviation of 28-day compressive strength decreased by 45%. This verifies that the process parameter control mechanism based on spatial distribution feedback effectively eliminates the quality dispersion problem caused by temperature differences within the kiln. Furthermore, when dealing with disturbances such as order insertions and equipment speed reductions, the average ineffective waiting time on the production line decreased by 40%, and the on-time order delivery rate increased to over 98%, fully demonstrating the core value of the reverse-order derivation cycle optimization strategy in improving the flexibility and adaptability of the production line.

[0077] Example 6 Figure 2 This is a structural schematic diagram of the intelligent management and control device for the entire life cycle of prefabricated components provided in Embodiment Six of the present invention, as shown below. Figure 2 As shown, the intelligent management and control device 100 for the entire life cycle of prefabricated components provided in Embodiment 6 of the present invention includes: a data acquisition module 110, a synchronization module 120, a processing module 130, and an execution module 140. The acquisition module 110 is used to acquire multi-source production data from multiple independent subsystems in the precast component production line; The synchronization module 120 is used to synchronize the multi-source production data to the pre-built digital twin model so as to drive the digital twin model to be updated in real time. The processing module 130 is used to call a preset intelligent decision-making model to process the multi-source production data gathered in the digital twin model to obtain a set of decision instructions for controlling the production line. The execution module 140 is used to feed back the decision instruction set to the target control terminal and execution equipment corresponding to the production line, so as to execute the control operation corresponding to the decision instruction set.

[0078] The intelligent management and control device 100 for the entire life cycle of prefabricated components provided in this embodiment six can realize the intelligent management and control method for the entire life cycle of prefabricated components in embodiment one, and has the same technical effect as embodiment one.

[0079] Example 7 Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in Embodiment 7 of the present invention. Figure 3 A block diagram is shown of an exemplary electronic device 12 suitable for implementing embodiments of the present invention. Figure 3 The electronic device 12 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0080] like Figure 3 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0081] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0082] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0083] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as "hard disk drives"). Disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disk drives for reading and writing to removable non-volatile optical disks (e.g., CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0084] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0085] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the electronic device 12 / server / computer, and / or with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 3 As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although... Figure 3 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0086] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the intelligent management and control method for the entire life cycle of prefabricated components provided in the embodiments of the present invention.

[0087] Example 8 Embodiment 8 of the present invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the intelligent management and control method for the entire life cycle of prefabricated components as provided in the above embodiments.

[0088] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0089] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0090] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0091] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0092] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for intelligent management and control of the entire life cycle of precast components, characterized in that, The method includes: Collect multi-source production data from multiple independent subsystems in the precast component production line; The multi-source production data is synchronized to the pre-built digital twin model to drive the digital twin model to be updated in real time. The preset intelligent decision-making model is invoked to process the multi-source production data gathered in the digital twin model to obtain a set of decision instructions for controlling the production line; The decision instruction set is fed back to the target control terminal and execution equipment corresponding to the production line to execute the control operation corresponding to the decision instruction set.

2. The intelligent management and control method for the entire life cycle of prefabricated components according to claim 1, characterized in that, The collection of multi-source production data from multiple independent subsystems in the precast component production line includes: The first type of data is collected from the warehouse control system. This first type of data includes the identification and flow location status information of molds and components in the production line conveying equipment, elevators and three-dimensional maintenance warehouse. The second type of data is collected from the manufacturing execution system. This second type of data is data that is bound to the component production order, including component process drawing information and quality inspection information. A third type of data is collected from IoT sensors deployed at the production site, including operating parameter information of the production equipment and environmental status information of the curing kiln.

3. The intelligent management and control method for the entire life cycle of prefabricated components according to claim 2, characterized in that, The step of synchronizing the multi-source production data to a pre-built digital twin model to drive the digital twin model to perform real-time updates includes: Using Building Information Modeling (BIM) as the geometric and information foundation, a digital twin model is constructed, which includes a production line layout model, a production equipment model, and a component model. Establish a data mapping relationship between the virtual entities in the digital twin model and the physical entities in the production line; Based on the data mapping relationship, the first type of data, the second type of data, and the third type of data are injected into and the state attributes of the corresponding virtual entities in the digital twin model are updated respectively.

4. The intelligent management and control method for the entire life cycle of prefabricated components according to claim 3, characterized in that, The step of invoking a preset intelligent decision-making model to process the multi-source production data aggregated in the digital twin model to obtain a set of decision instructions for controlling the production line includes: The preset intelligent decision-making model performs timestamp alignment and correlation fusion on the updated first type of data, second type of data and third type of data in the digital twin model to generate a full-process tracking data chain with a single component as the granularity. The preset intelligent decision-making model analyzes and calculates based on the full-process tracking data chain to generate a set of decision instructions that includes production cycle optimization instructions, equipment predictive maintenance instructions, and process parameter control instructions.

5. The intelligent management and control method for the entire life cycle of prefabricated components according to claim 4, characterized in that, The generation of the decision instruction set, which includes production cycle optimization instructions, predictive equipment maintenance instructions, and process parameter control instructions, includes: The preset intelligent decision-making model extracts the current queue length and historical average operation time of each workstation based on the full-process tracking data chain, calculates the current bottleneck workstation of the production line through the preset blockage rate evaluation algorithm, and, in combination with the order delivery time window, reverse-derives and generates the production cycle optimization instruction with the minimum waiting time. The preset intelligent decision-making model is based on the full-process tracking data chain, extracts multi-dimensional operating parameters of the associated equipment to construct the equipment health baseline curve, and uses a sliding time window to monitor the real-time fluctuation trend of the parameters. When the degree of deviation of the parameters from the health baseline curve exceeds the preset dynamic threshold range, it is determined as a potential fault point and generates the equipment predictive maintenance instruction containing the urgency level and maintenance suggestions. The preset intelligent decision-making model is based on the full-process tracking data chain, analyzes the standard curing process curve corresponding to the current component type, and obtains the temperature and humidity distribution cloud map in the curing kiln in the digital twin model in real time. By comparing the deviation between the standard curve and the real-time distribution, it dynamically calculates the start and stop time and power ratio of the heating or humidifying equipment, and generates refined process parameter control instructions.

6. The intelligent management and control method for the entire life cycle of prefabricated components according to claim 5, characterized in that, The step of feeding back the decision instruction set to the target control terminal and execution equipment corresponding to the production line includes: The production cycle optimization command is sent to the central scheduling controller of the production line to adjust the coordinated operation rhythm of each conveying device and robot on the production line. The predictive maintenance instructions for the equipment are pushed to the equipment management terminal interface and the mobile terminal of the maintenance personnel for visual alarms and maintenance prompts. The process parameter control commands are sent to the environmental control system of the curing kiln to perform precise temperature and humidity adjustments.

7. The intelligent management and control method for the entire life cycle of precast components according to any one of claims 1 to 6, characterized in that, The method further includes: The system receives response data from the target control terminal and the execution device after performing the control operation, and inputs the response data as new multi-source production data into the digital twin model. Through the updating of the digital twin model and the processing of the preset intelligent decision model, a closed-loop intelligent control process for the production line is formed.

8. A precast component full life cycle intelligent management and control device, characterized in that, include: The data acquisition module is used to collect multi-source production data from multiple independent subsystems in the precast component production line; The synchronization module is used to synchronize the multi-source production data to the pre-built digital twin model to drive the digital twin model to be updated in real time. The processing module is used to call a preset intelligent decision-making model to process the multi-source production data gathered in the digital twin model to obtain a set of decision instructions for controlling the production line. The execution module is used to feed back the decision instruction set to the target control terminal and execution equipment corresponding to the production line, so as to execute the control operation corresponding to the decision instruction set.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; When the processor executes the computer execution instructions stored in the memory, it is used to implement the intelligent management and control method for the entire life cycle of prefabricated components as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the intelligent management and control method for the entire life cycle of prefabricated components as described in any one of claims 1 to 7.